[ 
https://issues.apache.org/jira/browse/YARN-5907?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Wangda Tan updated YARN-5907:
-----------------------------
    Description: 
container requests to the AM should be able to request anti-affinity to ensure 
that things like Region Servers don't come up on the same failure zones. 

Similarly, you may be able to want to specify affinity to same host or rack 
without specifying which specific host/rack. Example: bringing up a small 
giraph cluster in a large YARN cluster would benefit from having the processes 
in the same rack purely for bandwidth reasons.

{color:red}
This JIRA is cloned umbrella JIRA of YARN-1042, discussions / designs / POC 
patches, etc. please refer to YARN-1042.
{color}

  was:
container requests to the AM should be able to request anti-affinity to ensure 
that things like Region Servers don't come up on the same failure zones. 

Similarly, you may be able to want to specify affinity to same host or rack 
without specifying which specific host/rack. Example: bringing up a small 
giraph cluster in a large YARN cluster would benefit from having the processes 
in the same rack purely for bandwidth reasons.


> [Umbrella] [YARN-1042] add ability to specify affinity/anti-affinity in 
> container requests
> ------------------------------------------------------------------------------------------
>
>                 Key: YARN-5907
>                 URL: https://issues.apache.org/jira/browse/YARN-5907
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: resourcemanager
>    Affects Versions: 3.0.0-alpha1
>            Reporter: Steve Loughran
>            Assignee: Wangda Tan
>
> container requests to the AM should be able to request anti-affinity to 
> ensure that things like Region Servers don't come up on the same failure 
> zones. 
> Similarly, you may be able to want to specify affinity to same host or rack 
> without specifying which specific host/rack. Example: bringing up a small 
> giraph cluster in a large YARN cluster would benefit from having the 
> processes in the same rack purely for bandwidth reasons.
> {color:red}
> This JIRA is cloned umbrella JIRA of YARN-1042, discussions / designs / POC 
> patches, etc. please refer to YARN-1042.
> {color}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org

Reply via email to